A Detection Method of FAQ Matching Inquiry E-mails by Automatic Generation of Characteristic Word Groups from Past Inquiry E-mails

Abstract

This paper discusses how to detect the inquiry e-mails corresponding to pre-defined FAQs (Frequently Asked Questions). Web-based interactions such as order and registration form on a Web page are usually provided with their FAQ pages for helping a user. However, most users submit their inquiry e-mails without checking such pages. This causes a help desk operator to process lots of e-mails even if some contents match FAQs. Automatic detecting of such e-mails is proposed based on SVM (Support Vector Machine) and specific Jaccard coefficient based on positive and negative already-received inquiry e-mails. Experimental results show its effectiveness, and we also discuss future work to improve our method.